{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T12:22:49Z","timestamp":1725711769651},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1109\/vcip59821.2023.10402629","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:35:59Z","timestamp":1706553359000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["MotionMLP: End-to-End Action Recognition with Motion Aware Vision MLP"],"prefix":"10.1109","volume":"27","author":[{"given":"Xiangning","family":"Ruan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]},{"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref2","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"article-title":"Videomae: Masked autoen-coders are data-efficient learners for self-supervised video pre-training","year":"2022","author":"Tong","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"24 261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"article-title":"As-mlp: An axial shifted mlp architecture for vision","year":"2021","author":"Lian","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.172"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00153"},{"article-title":"Efficient video representation learning via masked video modeling with motion-centric token selection","year":"2022","author":"Hwang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref31","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume":"33","author":"Han","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-023-01444-9"},{"article-title":"Xkd: Cross-modal knowledge distillation with domain alignment for video representation learning","year":"2022","author":"Sarkar","key":"ref35"}],"event":{"name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2023,12,4]]},"location":"Jeju, Korea, Republic of","end":{"date-parts":[[2023,12,7]]}},"container-title":["2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10402600\/10402106\/10402629.pdf?arnumber=10402629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:16:53Z","timestamp":1706793413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10402629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/vcip59821.2023.10402629","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}